Optimal Dispatch in Emergency Service System via Reinforcement Learning

TL;DR

This paper models ambulance dispatch as a Markov decision process and introduces reinforcement learning techniques to optimize resource allocation, demonstrating improved policies over traditional methods.

Contribution

It presents a novel reinforcement learning approach using post-decision states for optimal ambulance dispatch with reduced computational complexity.

Findings

Temporal-difference policy outperforms myopic policy

Proposed methods improve emergency response efficiency

Minimal cost required for performance enhancement

Abstract

In the United States, medical responses by fire departments over the last four decades increased by 367%. This had made it critical to decision makers in emergency response departments that existing resources are efficiently used. In this paper, we model the ambulance dispatch problem as an average-cost Markov decision process and present a policy iteration approach to find an optimal dispatch policy. We then propose an alternative formulation using post-decision states that is shown to be mathematically equivalent to the original model, but with a much smaller state space. We present a temporal difference learning approach to the dispatch problem based on the post-decision states. In our numerical experiments, we show that our obtained temporal-difference policy outperforms the benchmark myopic policy. Our findings suggest that emergency response departments can improve their performance with minimal to no cost.